Minimize D&D spell extraction contracts

docs/internal/llm.md

@@ -134,8 +134,8 @@ reusable content follows it.
 
 Accordingly, the common prefix of all three extraction prompts is system,
 extraction evidence, identity, and campaign references. The NPC prompt then
-renders task, instructions, and transcript. Spell renders immediate resolution,
-NPC registry, catalog, task, instructions, and transcript. Combat renders
+renders task, instructions, and transcript. Spell renders the NPC registry,
+catalog, task, instructions, and transcript. Combat renders
 immediate resolution, NPC registry, task, instructions, and transcript. The
 scene chunker is not an extraction lane: it retains its separate system,
 transcript, campaign-reference, task, and instruction order and marks its

docs/internal/modules.md

@@ -207,16 +207,13 @@ failures therefore stop construction before source parsing or an LLM call;
 campaign references remain separate disambiguation inputs and never become
 source evidence.
 
-The prompt limits each cast to its declaration and immediate resolution; it
-does not follow summoned creatures, persistent effects, or other downstream
-consequences through the scene. Shared extraction-evidence and identity rules
-require transcript-supported factual claims and the most specific in-world
-caster identity, while campaign references only disambiguate source text.
-Effects describe the session as played: model rules knowledge cannot supplement
-or correct the transcript, and nonstandard adjudication is attributed to the GM
-or table rather than stated as a universal rule. Structural source validation
-remains deterministic; semantic claim completeness is enforced through
-extraction policy and evaluation.
+The prompt includes only actual casting events and unambiguous declared casting
+attempts. Spell mentions, plans, rules discussion, and catalog matches without
+a casting event are excluded. Shared extraction-evidence and identity rules
+require transcript-supported caster and spell facts, while the catalog,
+campaign references, and NPC names only disambiguate source text. Structural
+source validation remains deterministic; semantic evidence sufficiency is
+enforced through extraction policy and evaluation.
 
 Both the extractor and deterministic catalog validator expose
 the effective base-plus-overlay semantic digest as scoped prepared-component
@@ -224,23 +221,23 @@ checkpoint identity. Raw overlay provenance independently covers file-byte
 changes, while the semantic digest also invalidates reuse when the embedded
 catalog or catalog composition changes. The extractor additionally fingerprints
 its complete prompt assets and private response schema, so either semantic
-contract changing invalidates previously recorded extraction checkpoints. The separate
-`internal/modules/dnd/codec/spells` package
+contract changing invalidates previously recorded extraction checkpoints. The
+separate `internal/modules/dnd/codec/spells` package
 owns the durable schema and stable JSON representation for artifact kind
 `dnd/spell-list`. The runner keeps the result typed through validators and later
 stages, using the codec only for checkpoint, debug, and output boundaries.
-Shared D&D helpers keep prompt input
-names and source-unit reference conversion consistent with the scene chunker.
+Shared D&D helpers keep prompt input names and source-unit reference conversion
+consistent with the scene chunker.
 
 The extractor also declares the optional `npcs` registry slot and consumes the
 immutable registry boundary from `internal/modules/dnd/npcs/registry`. An
 external registry is prepared before execution; a generated registry is
-validated and supplied at operation time. External bindings may add only
-`npc_registry_digest` and `npc_count` to module metadata and an
-`npc_registry` checkpoint fingerprint. Generated bindings are represented by
+validated and supplied at operation time. Bound external registries add only
+the full `npc_registry_digest` and `npc_count` to module metadata. The local
+`npc_registry` checkpoint fingerprint always covers the names-only projection,
+including its exact unbound value. Generated bindings are represented by
 framework handoff provenance and dependency fingerprints. The unbound prompt
-input is exactly `{"npcs":[]}`, has a projection fingerprint, and has no
-registry provenance.
+input is exactly `{"npcs":[]}` and has no registry provenance.
 The shared NPC grounding fragment is placed immediately after the common
 campaign reference message and is included in the spell prompt fingerprint.
 
@@ -321,9 +318,9 @@ scoped warnings for each mutation or unresolved name.
 After those per-cast changes, it collapses only casts with the same canonical
 spell, case-folded and whitespace-normalized caster, and complete non-empty
 valid source-reference set. It retains the first occurrence and its caster,
-effect, narrative description, and stable order. Unknown names, empty or
-invalid evidence, and adjacent or overlapping but different ranges remain
-unchanged for validation.
+source references, and stable order. Unknown names, empty or invalid evidence,
+and adjacent or overlapping but different ranges remain unchanged for
+validation.
 
 The normalizer exposes the effective catalog digest as its independently scoped
 `effective_catalog` checkpoint fingerprint and reports catalog base ID, digest,
@@ -378,11 +375,11 @@ codec bytes according to its target context. Neither validator calls the LLM.
 ## D&D Spell Validators
 
 All four validators receive `dnd.SpellList` directly. The shape validator
-rejects missing or empty spell fields and empty reference lists. The catalog
-validator defers when shape is invalid, then checks every non-empty spell name
-against the immutable effective SRD and overlay catalog. It accepts normalized
-canonical names and aliases without rewriting the artifact; unknown names
-reject the complete result with bounded, stable index/name diagnostics. The
+rejects a missing list, blank caster or spell names, and empty reference lists.
+The catalog validator defers when shape is invalid, then checks every non-empty
+spell name against the immutable effective SRD and overlay catalog. It accepts
+normalized canonical names and aliases without rewriting the artifact; unknown
+names reject the complete result with bounded, stable index/name diagnostics. The
 source-reference validator defers malformed shapes, validates every cited
 range, and reports all range defects through a bounded aggregate while
 preserving `invalid_source_refs`. The relatedness validator resolves all cited

docs/internal/overview.md

@@ -115,11 +115,13 @@ this package. Domain-neutral prompt filesystem composition lives in
 The `dnd/npcs/registry` package owns the optional `npcs` registry boundary.
 External references are strictly decoded and identity-validated during
 preparation; generated references are decoded and identity-validated at the
-ordered step handoff. Both paths emit canonical registry JSON to operation-time
-spell and combat prompt or normalization requests. The framework records
-generated identity and bounded producer provenance, while the raw external
-reference remains independently tracked by pipeline provenance. An absent
-registry is represented only by the empty prompt value `{"npcs":[]}`. Spell
+ordered step handoff. Both paths retain canonical registry JSON for provenance
+and emit a names-only projection to operation-time spell and combat prompts.
+Combat normalization uses the canonical registry for exact actor lookup. The
+framework records generated identity and bounded producer provenance, while
+the raw external reference remains independently tracked by pipeline
+provenance. An absent registry is represented only by the empty prompt value
+`{"npcs":[]}`. Spell
 and combat consumers use this shared boundary without changing their public
 module contracts.